INDEX

Explanations

numerical quantities, specifically quantities that indicate a specific count or amount

oai_token-act-pair · gpt-3.5-turbo

repeated occurrences of the phrase "at" followed by a numerical value or a reference to time

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.hook_resid_pre

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

torch.float32

Hook Point

blocks.5.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

FTWARE

-0.73

aceutical

-0.68

powder

-0.65

clean

-0.64

alpha

-0.63

Tube

-0.61

adoes

-0.61

tools

-0.60

 thereof

-0.59

monkey

-0.57

POSITIVE LOGITS

 least

1.16

mosp

1.03

hens

0.93

kinson

0.89

 times

0.88

chieve

0.86

onement

0.80

ention

0.79

roph

0.78

£ı

0.76

Activations Density 0.085%

numerical quantities, specifically quantities that indicate a specific count or amount

repeated occurrences of the phrase "at" followed by a numerical value or a reference to time

No Comments

No Known Activations